Linear and neural network models for predicting N-glycosylation in Chinese Hamster Ovary cells based on B4GALT levels

Abstract

Glycosylation is an essential modification to proteins that has positive effects, such as improving the half-life of antibodies, and negative effects, such as promoting cancers. Despite the importance of glycosylation, data-driven models to predict quantitative N-glycan distributions have been lacking. This article constructs linear and neural network models to predict the distribution of glycans on N-glycosylation sites. The models are trained on data containing normalized B4GALT1–B4GALT4 levels in Chinese Hamster Ovary cells. The ANN models achieve a median prediction error of 1.59% on an independent test set, an error 9-fold smaller than for previously published models using the same data, and a narrow error distribution. We also discuss issues with other models in the literature and the advantages of this work’s model over other data-driven models. We openly provide all of the software used, allowing other researchers to reproduce the work and reuse or improve the code in future endeavors.